J

donaldJJ's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in ggml-org/Qwen3.8-27B-GGUF 13 days ago

Measured VRAM for Q4_K_M: 18.42 GiB at 8K, 19.95 GiB at 32K (llama.cpp, flash attention)

#6 opened 13 days ago by

donaldJJ

updated a dataset 25 days ago

donaldJJ/llm-vram-requirements

Viewer • Updated 26 days ago • 64 • 148

updated a Space 25 days ago

Running

LLM VRAM Calculator

📊

Paste a HF model id, get VRAM for any quant and context

New activity in Qwen/Qwen3.8-Flash-Next 26 days ago

Model cannot SPLIT TENSOR and will not work in consumer multi gpu

😔 1

3

#62 opened about 1 month ago by

Dr-Ojinsky

New activity in unsloth/Qwen3.8-27B-GGUF 26 days ago

Which GGUF quantization would you recommend for an RTX 5080 (16GB VRAM)?

5

#131 opened about 1 month ago by

pengwenzhi

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 26 days ago

Running IQ4_XS with MTP , crashing after a while.

➕ 1

2

#74 opened about 1 month ago by

Oxidez

New activity in yandex/AliceAI-Foundation-80B-A3B-Base 26 days ago

Квантование GGUF - Q8_0 и Q4_K_M

👍 1

2

#9 opened about 1 month ago by

itxw

New activity in XiaomiMiMo/MiMo-V2.6-Pro-RL 26 days ago

Native quant?

👀 1

3

#1 opened about 1 month ago by

singulariti

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 26 days ago

for 16gb vram context size <=114688 is fast. Pelican is gorgeous :)

🤯👍 4

8

#56 opened about 1 month ago by

KottCh

Memory performance

👀 1

3

#67 opened about 1 month ago by

trombonator

New activity in incoai/Qwen3.8-27B-Splash 26 days ago

Can we have a 8bit target ?

👍 1

1

#12 opened 30 days ago by

trigger2k25

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF 26 days ago

Could we have a IQ3_S for coder?

🚀🔥 3

6

#3 opened 28 days ago by

alexaione

New activity in ukisai/Swift-1.5-Qwen3.8-27B-GGUF 26 days ago

MTP working?

4

#4 opened 28 days ago by

netomx

New activity in bottlecapai/ThinkingCap-Qwen3.8-27B-GGUF 26 days ago

Can you guys supply the Q5_K_M version?

❤️ 3

5

#4 opened about 1 month ago by

slyfox1186

New activity in ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF 26 days ago

Q4 for 64GB devices

🔥 3

3

#1 opened about 1 month ago by

Vasili-Sk

New activity in paradigma-inc/limite-1b-violetto 26 days ago

VRAM requirements table / optional README badge

👍 1

#2 opened 26 days ago by

donaldJJ

New activity in TaichuAI/ZDTaichu5.0-9B 26 days ago

VRAM requirements table / optional README badge

#4 opened 26 days ago by

donaldJJ

New activity in XingChen-AGI/Xing4.0-29B-A4B 26 days ago

VRAM requirements table / optional README badge

#13 opened 26 days ago by

donaldJJ

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF 26 days ago

Speed tests on a 3060 laptop with 48GB RAM

2

#31 opened 27 days ago by

2vibeornot2vibe

New activity in ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF 26 days ago

Pretty good performance on a 2016 card

4

#5 opened 27 days ago by

ygboucherk